Analyzing Financial Statements Skill

The Analyzing Financial Statements Skill is a highly precise operational skill for AI agents, sourced directly from Anthropic's official claude-cookbooks repository under skills/custom_skills/analyzing-financial-statements. This skill equips large language models such as Claude Code, ChatGPT, or Cursor with the rigorous financial frameworks and mathematical algorithms required to structure, analyze, and interpret balance sheets, income statements, and cash flow statements for corporate evaluations and investment analysis.

Capabilities Imparted to the Agent

Evaluating dense financial filings (such as 10-K or 10-Q reports) is highly time-consuming for human analysts and prone to mathematical errors when executed by untrained AI models. This skill solves this challenge by embedding a structured, rule-based analysis methodology into the AI's core instructions. When raw financial statements are provided, the agent loads this skill to perform deterministic ratio calculations.

The skill covers the following financial core domains:
Liquidity Ratios: Accurate computation of Working Capital, Current Ratio, and Quick Ratio to evaluate the short-term solvency of a business.
Profitability Ratios: Evaluation of Gross Profit Margin, Operating Margin, Net Profit Margin, as well as capital efficiency metrics such as Return on Assets (ROA) and Return on Equity (ROE).
Solvency and Leverage: Analysis of capital structures by calculating Debt-to-Equity and Interest Coverage ratios to evaluate debt service capacity.
DuPont Framework & Trends: Multi-year trend analysis and deep decomposition of ROE using the DuPont framework to highlight operational levers.

Data Structure and Mathematical Precision

To guarantee computational accuracy, the skill instructs the AI to first parse raw text statements into structured JSON arrays or structured matrices before running mathematical functions. Every calculated ratio must be accompanied by its formula and the exact raw inputs sourced from the reports. This guarantees full auditability for the human user, allowing them to trace every step and completely eliminating AI calculation hallucinations.

Input Formats, Ratios and Results

According to the cookbook, the skill accepts financial data as CSV with financial line items, as JSON with structured statements, as a text description of the key figures, or as an Excel file. Its efficiency ratios include Asset Turnover, Inventory Turnover and Receivables Turnover, and its valuation ratios include P/E, P/B, P/S, EV/EBITDA and PEG. Per-share metrics such as earnings per share (EPS), book value per share and dividend per share are covered as well. The result contains the calculated ratios, industry benchmark comparisons, trend analysis, an interpretation and a formatted Excel report. The script calculate_ratios.py performs the calculation, and interpret_ratios.py provides the interpretation and benchmarking. The provider names limits: the data must be accurate, the benchmarks rely on general guidelines, not every ratio applies to every industry, and past figures do not guarantee future performance.

Boundaries and Licensing

This catalog record represents the instructional skill (prompts and operational guidelines) configured within your AI client's memory or system prompt, rather than an executable application or API endpoint. The claude-cookbooks repository is open-sourced under the MIT license, boasting over 32,600 stars on GitHub as of September 2026. The skill is entirely free to adopt and open-source.

Benefits and Evaluation

For venture capitalists, financial analysts, startup founders, and accountants, this skill is an invaluable asset that transforms raw spreadsheet balance sheets into professional investment memos or audit summaries in seconds. It fits perfectly into the Data Analysis and Office productivity sections of the *Skill Road* catalog.